Skill Evals
$
npx mdskill add aaronjmars/aeon/Skill EvalsSkill Evals identifies and flags quality regressions between runs
- Identifies changes in skill outputs compared to previous evaluations.
- Deploys assertions for validation against expected outcomes.
- Compares current results with prior evaluations to detect regressions or new failures.
- Files issues for identified problems and queues fixes for manual review.
SKILL.md
.github/skills/Skill EvalsView on GitHub ↗
No skill content available yet.